{ "item_title" : "Securing AI Agents", "item_author" : [" Aveek SenGupta "], "item_description" : "AI agents don't just answer questions anymore. They run code, call APIs, change databases, and make decisions on their own. The security frameworks most teams rely on were never designed for software that acts autonomously.Securing AI Agents is a hands-on guide to the vulnerabilities that appear when large language models start doing things instead of just saying things. Across 16 chapters, each attack surface is paired with working defenses: prompt injection, tool misuse, memory poisoning, goal hijacking, runaway loops, and missing audit trails.Readers break things first. Each chapter starts with a vulnerable implementation, shows exactly how it fails, then walks through a hardened version. All 841 tests run locally with Python and pytest. No API keys. No cloud accounts.The book also covers multi-agent security architecture, red teaming, and compliance mapping to the EU AI Act, NIST AI RMF, OWASP LLM Top 10, and MITRE ATLAS, connecting regulatory language to controls that engineering teams can ship.Written for anyone building, auditing, or evaluating agentic systems.", "item_img_path" : "https://covers1.booksamillion.com/covers/bam/9/79/890/763/9798907639928_b.jpg", "price_data" : { "retail_price" : "21.99", "online_price" : "21.99", "our_price" : "21.99", "club_price" : "21.99", "savings_pct" : "0", "savings_amt" : "0.00", "club_savings_pct" : "0", "club_savings_amt" : "0.00", "discount_pct" : "10", "store_price" : "" } }

Overview

Customers Also Bought

Details